Self-Supervised Keypoint Discovery in Behavioral Videos
Abstract
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main sources of movement in behavioral videos, our method uses an encoder-decoder architecture with a geometric bottleneck to reconstruct the difference between video frames. By focusing only on regions of movement, our approach works directly on input videos without requiring manual annotations, such as keypoints or bounding boxes. Experiments on a variety of agent types (mouse, fly, human, jellyfish, and trees) demonstrate the generality of our approach and reveal that our discovered keypoints represent semantically meaningful body parts, which achieve state-of-the-art performance on keypoint regression among self-supervised methods. Additionally, our discovered keypoints achieve comparable performance to supervised keypoints on downstream tasks, such as behavior classification, suggesting that our method can dramatically reduce the cost of model training vis-a-vis supervised methods.
Additional Information
This work was generously supported by the Simons Collaboration on the Global Brain grant 543025 (to PP and DJA), NIH Award #R00MH117264 (to AK), NSF Award #1918839 (to YY), NINDS Award #K99NS119749 (to BW), NIH Award #R01MH123612 (to DJA, PP, and SR), NSERC Award #PGSD3-532647-2019 (to JJS), as well as a gift from Charles and Lily Trimble (to PP).Attached Files
Submitted - 2112.05121.pdf
Files
Name | Size | Download all |
---|---|---|
md5:523c6cb716191efa16aab7f609fdd9a7
|
46.5 MB | Preview Download |
Additional details
- Eprint ID
- 113586
- Resolver ID
- CaltechAUTHORS:20220224-200833645
- Simons Foundation
- 543025
- NIH
- R00MH117264
- NSF
- CCF-1918839
- NIH
- K99NS119749
- NIH
- R01MH123612
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- PGSD3-532647-2019
- Charles and Lily Trimble
- Created
-
2022-02-28Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field
- Caltech groups
- Tianqiao and Chrissy Chen Institute for Neuroscience, GALCIT, Division of Biology and Biological Engineering